© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35027
    Prev
    Next
    INDEX
    Explanations

    in front of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =-\
    0.69
    x
    0.69
    מ
    0.68
    很
    0.66
    }.
    0.63
    Depends
    0.63
     efectuar
    0.63
    Expend
    0.60
    ParentElement
    0.60
    }:
    0.59
    POSITIVE LOGITS
    л
    0.91
    er
    0.73
     eukaryotic
    0.71
    uk
    0.69
    äle
    0.69
    ر
    0.68
    urow
    0.67
    ர்ஸ்
    0.66
    ר
    0.64
    at
    0.63
    Activations Density 0.001%

    No Known Activations